1 Introduction to data visualization

## Loading required package: ggplot2

## 
## Attaching package: 'reshape2'

## The following object is masked from 'package:tidyr':
## 
##     smiths

## 
## Attaching package: 'reshape'

## The following objects are masked from 'package:reshape2':
## 
##     colsplit, melt, recast

## The following objects are masked from 'package:tidyr':
## 
##     expand, smiths

## 
## Attaching package: 'ggh4x'

## The following object is masked from 'package:ggplot2':
## 
##     guide_axis_logticks

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:reshape':
## 
##     rename

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

## Loading required package: viridis

## Loading required package: viridisLite

## 
## ======================
## Welcome to heatmaply version 1.5.0
## 
## Type citation('heatmaply') for how to cite the package.
## Type ?heatmaply for the main documentation.
## 
## The github page is: https://github.com/talgalili/heatmaply/
## Please submit your suggestions and bug-reports at: https://github.com/talgalili/heatmaply/issues
## You may ask questions at stackoverflow, use the r and heatmaply tags: 
##   https://stackoverflow.com/questions/tagged/heatmaply
## ======================

## [[1]]
## [1] "ggpubr"    "ggplot2"   "stats"     "graphics"  "grDevices" "utils"    
## [7] "datasets"  "methods"   "base"     
## 
## [[2]]
##  [1] "grid"      "ggpubr"    "ggplot2"   "stats"     "graphics"  "grDevices"
##  [7] "utils"     "datasets"  "methods"   "base"     
## 
## [[3]]
##  [1] "tidyr"     "grid"      "ggpubr"    "ggplot2"   "stats"     "graphics" 
##  [7] "grDevices" "utils"     "datasets"  "methods"   "base"     
## 
## [[4]]
##  [1] "reshape2"  "tidyr"     "grid"      "ggpubr"    "ggplot2"   "stats"    
##  [7] "graphics"  "grDevices" "utils"     "datasets"  "methods"   "base"     
## 
## [[5]]
##  [1] "reshape"   "reshape2"  "tidyr"     "grid"      "ggpubr"    "ggplot2"  
##  [7] "stats"     "graphics"  "grDevices" "utils"     "datasets"  "methods"  
## [13] "base"     
## 
## [[6]]
##  [1] "ggrepel"   "reshape"   "reshape2"  "tidyr"     "grid"      "ggpubr"   
##  [7] "ggplot2"   "stats"     "graphics"  "grDevices" "utils"     "datasets" 
## [13] "methods"   "base"     
## 
## [[7]]
##  [1] "ggh4x"     "ggrepel"   "reshape"   "reshape2"  "tidyr"     "grid"     
##  [7] "ggpubr"    "ggplot2"   "stats"     "graphics"  "grDevices" "utils"    
## [13] "datasets"  "methods"   "base"     
## 
## [[8]]
##  [1] "pheatmap"  "ggh4x"     "ggrepel"   "reshape"   "reshape2"  "tidyr"    
##  [7] "grid"      "ggpubr"    "ggplot2"   "stats"     "graphics"  "grDevices"
## [13] "utils"     "datasets"  "methods"   "base"     
## 
## [[9]]
##  [1] "RColorBrewer" "pheatmap"     "ggh4x"        "ggrepel"      "reshape"     
##  [6] "reshape2"     "tidyr"        "grid"         "ggpubr"       "ggplot2"     
## [11] "stats"        "graphics"     "grDevices"    "utils"        "datasets"    
## [16] "methods"      "base"        
## 
## [[10]]
##  [1] "patchwork"    "RColorBrewer" "pheatmap"     "ggh4x"        "ggrepel"     
##  [6] "reshape"      "reshape2"     "tidyr"        "grid"         "ggpubr"      
## [11] "ggplot2"      "stats"        "graphics"     "grDevices"    "utils"       
## [16] "datasets"     "methods"      "base"        
## 
## [[11]]
##  [1] "DT"           "patchwork"    "RColorBrewer" "pheatmap"     "ggh4x"       
##  [6] "ggrepel"      "reshape"      "reshape2"     "tidyr"        "grid"        
## [11] "ggpubr"       "ggplot2"      "stats"        "graphics"     "grDevices"   
## [16] "utils"        "datasets"     "methods"      "base"        
## 
## [[12]]
##  [1] "kableExtra"   "DT"           "patchwork"    "RColorBrewer" "pheatmap"    
##  [6] "ggh4x"        "ggrepel"      "reshape"      "reshape2"     "tidyr"       
## [11] "grid"         "ggpubr"       "ggplot2"      "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"        
## 
## [[13]]
##  [1] "plotly"       "kableExtra"   "DT"           "patchwork"    "RColorBrewer"
##  [6] "pheatmap"     "ggh4x"        "ggrepel"      "reshape"      "reshape2"    
## [11] "tidyr"        "grid"         "ggpubr"       "ggplot2"      "stats"       
## [16] "graphics"     "grDevices"    "utils"        "datasets"     "methods"     
## [21] "base"        
## 
## [[14]]
##  [1] "bookdown"     "plotly"       "kableExtra"   "DT"           "patchwork"   
##  [6] "RColorBrewer" "pheatmap"     "ggh4x"        "ggrepel"      "reshape"     
## [11] "reshape2"     "tidyr"        "grid"         "ggpubr"       "ggplot2"     
## [16] "stats"        "graphics"     "grDevices"    "utils"        "datasets"    
## [21] "methods"      "base"        
## 
## [[15]]
##  [1] "heatmaply"    "viridis"      "viridisLite"  "bookdown"     "plotly"      
##  [6] "kableExtra"   "DT"           "patchwork"    "RColorBrewer" "pheatmap"    
## [11] "ggh4x"        "ggrepel"      "reshape"      "reshape2"     "tidyr"       
## [16] "grid"         "ggpubr"       "ggplot2"      "stats"        "graphics"    
## [21] "grDevices"    "utils"        "datasets"     "methods"      "base"

## Bioconductor version '3.19' is out-of-date; the current release version '3.20'
##   is available with R version '4.4'; see https://bioconductor.org/install

## Bioconductor version 3.19 (BiocManager 1.30.25), R 4.4.1 (2024-06-14)

## Warning: package(s) not installed when version(s) same as or greater than current; use
##   `force = TRUE` to re-install: 'ComplexHeatmap'

## Old packages: 'bookdown', 'clue', 'corrplot', 'curl', 'data.table',
##   'dendextend', 'doBy', 'emmeans', 'evaluate', 'fs', 'GenomicRanges', 'gert',
##   'gtable', 'Hmisc', 'httr2', 'igraph', 'knitr', 'Matrix', 'mvtnorm',
##   'pkgbuild', 'ps', 'quantreg', 'R.oo', 'Rcpp', 'renv', 'rmarkdown',
##   'rstudioapi', 'tinytex', 'waldo', 'withr', 'xfun'

2 Downloading the files and making a Dir called Raw

3 Loading the first file

# Load the TSV files
alpha_info_tab <- read.table("data/raw/01_Alpha_Diversity.tsv", header=T, sep="\t", row.names=1, check.names=T)
#ord_dataframe <- read.table("data/raw/02_ord_DataFrame.tsv", header = TRUE, sep = "\t")
#heatmap_exp1 <- read.table("data/raw/03_HeatMap_Exp1_DCs.tsv", header = TRUE, sep = "\t")

# Load the RDS file
#heatmap_data <- readRDS("data/raw/04_HeatMap.rds")

# Load the CSV file
#data_csv <- read.csv("data/raw/data.csv")

4 Summary: Sample Information

5 Filtering the data using Dyplr package

# Load dplyr


# Filter the data for Study == "Exp1"
alpha_info_tab_filtered <- alpha_info_tab %>%
  filter(Study == "Exp1")

# View the filtered data
alpha_info_tab_filtered

6 BoxPlot

#library(dplyr)
#library(ggplot2)

# Filter for Exp1 and create the boxplot
alpha_info_tab %>%
  filter(Study == "Exp1") %>%
  ggplot(aes(x = Compartment, y = Observed, fill = Compartment)) +
  geom_boxplot() +
  #geom_jitter(width = 0.2) +  # Adds individual data points
  theme_pubr(border = TRUE) +
  labs(x = "Compartment", y = "Observed") +
  ggtitle("Boxplot of Observed Values in Exp1 by Compartment") #+

  #scale_fill_manual(values = cols_compartment)

7 Sort the compartment and add color

# Different ways, by hand is useful for small data
cols_compartment <- c("Fecal" = "#D46C4E", "AC" = "#77A515", "TC" = "#264D59", "DC" = "#43978D")


# Using color brewer
# Get the unique compartments
unique_compartments <- unique(alpha_info_tab_filtered$Compartment)

# Automatically generate a color palette (you can use a predefined set or any other color scale)
cols_compartment_auto <- setNames(
  RColorBrewer::brewer.pal(length(unique_compartments), "Set3"), 
  unique_compartments
)

8 Plotting

# Filter for Exp1, reorder Compartment, and create the boxplot
alpha_info_tab %>%
  filter(Study == "Exp1") %>%
  mutate(Compartment = factor(Compartment, levels = c("Fecal", "AC", "TC", "DC"))) %>%
  ggplot(aes(x = Compartment, y = Observed, fill = Compartment)) +
  geom_boxplot() +
  theme_pubr(border = TRUE) +
  labs(x = "Compartment", y = "Observed") +
  ggtitle("Boxplot of Observed Values in Exp1 by Compartment") +
  scale_fill_manual(values = cols_compartment)

  #scale_fill_manual(values = cols_compartment_auto)# Assuming 'cols_compartment' contains your custom colors
# Saving
#ggsave("/Users/flb202/Documents/KU/BRIC/Projects/Arnes_Kristina/Results/03_PCAPlot.png", PCAPlot, width = 8.0, height = 5.5)

9 facet_wrap() funcion, mutate

#library(dplyr)
#library(ggplot2)

test <- alpha_info_tab %>%
  filter(Study == "Exp1") %>%  # Filter for Study "Exp1"
  # Create a new column `Units` that duplicates Fecal for both Unit1 and Unit2
  bind_rows(
    alpha_info_tab %>%
      filter(Compartment == "Fecal") %>%
      mutate(Units = "Unit1"),
    alpha_info_tab %>%
      filter(Compartment == "Fecal") %>%
      mutate(Units = "Unit2"),
    alpha_info_tab %>%
      filter(Compartment != "Fecal") %>%
      mutate(Units = as.character(Unit))  # Keep original Unit for other compartments
  ) %>%
  mutate(Compartment = factor(Compartment, levels = c("Fecal", "AC", "TC", "DC"))) %>%
  # Remove rows with NA in Compartment or Units columns
  filter(!is.na(Compartment) & !is.na(Units)) %>%
  ggplot(aes(x = Compartment, y = Observed, fill = Compartment)) +
  geom_boxplot() +  # Create the boxplot
  theme_pubr(border = TRUE) +  # Apply the theme
  labs(x = "Compartment", y = "Observed") +
  ggtitle("Boxplot of Observed Values in Exp1 by Compartment and Units") +
  scale_fill_manual(values = cols_compartment) +  # Apply custom colors
  facet_wrap(~ Units, scales = "free_x")
test

9.1 Longitudinal

# Extra

# Define the y-axis scale
#scales <- scale_y_continuous(limits = c(0, 129))

# Plotting
alpha_info_tab %>%
  filter(Study == "Exp1") %>%  # Filter for Exp1
  gather(key = "metric", value = "value", c("Observed", "Shannon")) %>%  # Reshape data
  mutate(
    metric = recode(metric, "Observed" = "Richness", "Shannon" = "Shannon")  # Change names directly in the data
  ) %>% 
  
  ggplot(aes(x = Day, y = value, color = Compartment, group = interaction(Study, Compartment_Unit))) +
  
  # Add vertical lines for day intervals
  geom_vline(xintercept = 1:23, linetype = 'solid', colour = "grey", alpha = 0.3) +
  
  # Plot points and lines
  geom_point(size = 4) +
  geom_line(aes(linetype = Unit)) +
  
  # Customize plot theme
  theme_pubr(border = TRUE) +
  theme(
    axis.text.x = element_text(size = 8, hjust = 0.5),
    axis.text.y = element_text(size = 8, hjust = 1),
    legend.position = "top"
  ) +
  
  # Custom color and line types
  scale_colour_manual(values = cols_compartment) +
  scale_linetype_manual(values = c("dotted", "solid", "dashed", "longdash")) +
  
  # Define x-axis labels
  scale_x_discrete(limits = c("Fecal", as.character(1:23))) +
  
  # Add labels for axes
  labs(x = "", y = "") +
  
  # Facet the plot by metric
  facet_grid(rows = vars(metric), scales = "free_y", space = "free_x") #+

  # Apply custom y-axis scale in facets (no labels, just limits)
  # facetted_pos_scales(y = scales)

Next Analysis

10 Beta Diversity, PCA

ord_DataFrame <- read.table("data/raw/02_ord_DataFrame.tsv",  header=T, sep="\t", row.names=1, check.names=T)

ord_DataFrame %>%
  knitr::kable() %>%
  kableExtra::kable_styling(bootstrap_options = c("striped", "hover"))

	X45.7.	X19.4.	Study	Unit	Compartment	Compartment_Unit	Day	Triplicate	Main_Analysis
Exp1_F2	-0.0700905	-0.3706615	Exp1	Fecal	Fecal	Fecal	0	A2	YES
Exp1_0A1	-0.0966809	-0.4513312	Exp1	Unit1	AC	AC1	1	NO	YES
Exp1_0A2	-0.0937636	-0.4653644	Exp1	Unit2	AC	AC2	1	NO	YES
Exp1_0D1	-0.0684402	-0.4998071	Exp1	Unit1	DC	DC1	1	NO	YES
Exp1_0D2	-0.0667823	-0.4909481	Exp1	Unit2	DC	DC2	1	NO	YES
Exp1_0T1	-0.0657618	-0.5205511	Exp1	Unit1	TC	TC1	1	NO	YES
Exp1_0T2	-0.0683041	-0.5175081	Exp1	Unit2	TC	TC2	1	NO	YES
Exp1_12A1_2	0.2511365	0.1368428	Exp1	Unit1	AC	AC1	12	A2	YES
Exp1_12A2_2	0.2469539	0.1242978	Exp1	Unit2	AC	AC2	12	A2	YES
Exp1_12D1_2	0.2474297	0.0501418	Exp1	Unit1	DC	DC1	12	A2	YES
Exp1_12D2_2	0.2456813	0.0240495	Exp1	Unit2	DC	DC2	12	A2	YES
Exp1_12T1_2	0.2700372	0.0961836	Exp1	Unit1	TC	TC1	12	A2	YES
Exp1_12T2_2	0.2668607	0.0869340	Exp1	Unit2	TC	TC2	12	A2	YES
Exp1_13A1	0.2525283	0.1310443	Exp1	Unit1	AC	AC1	13	NO	YES
Exp1_13A2	0.2501388	0.1338156	Exp1	Unit2	AC	AC2	13	NO	YES
Exp1_13D1	0.2446710	0.0737441	Exp1	Unit1	DC	DC1	13	NO	YES
Exp1_13D2	0.2480532	0.0465521	Exp1	Unit2	DC	DC2	13	NO	YES
Exp1_13T1	0.2668749	0.1237862	Exp1	Unit1	TC	TC1	13	NO	YES
Exp1_13T2	0.2636917	0.0934710	Exp1	Unit2	TC	TC2	13	NO	YES
Exp1_15A1	0.2529885	0.1382319	Exp1	Unit1	AC	AC1	15	NO	YES
Exp1_15A2	0.2574696	0.1464790	Exp1	Unit2	AC	AC2	15	NO	YES
Exp1_15D1	0.2225984	0.0710222	Exp1	Unit1	DC	DC1	15	NO	YES
Exp1_15D2	0.2452289	0.0477370	Exp1	Unit2	DC	DC2	15	NO	YES
Exp1_15T1	0.2572078	0.1080404	Exp1	Unit1	TC	TC1	15	NO	YES
Exp1_15T2	0.2601346	0.1038236	Exp1	Unit2	TC	TC2	15	NO	YES
Exp1_16A1	0.2543099	0.1239164	Exp1	Unit1	AC	AC1	16	NO	YES
Exp1_16A2	0.2579028	0.1278760	Exp1	Unit2	AC	AC2	16	NO	YES
Exp1_16D1	0.2231274	0.0715852	Exp1	Unit1	DC	DC1	16	NO	YES
Exp1_16D2	0.2262388	0.0555737	Exp1	Unit2	DC	DC2	16	NO	YES
Exp1_16T1	0.2553281	0.1097970	Exp1	Unit1	TC	TC1	16	NO	YES
Exp1_16T2	0.2555997	0.1028882	Exp1	Unit2	TC	TC2	16	NO	YES
Exp1_17A1_2	0.2571796	0.1348213	Exp1	Unit1	AC	AC1	17	A2	YES
Exp1_17A2_2	0.2567410	0.1364964	Exp1	Unit2	AC	AC2	17	A2	YES
Exp1_17D1_2	0.2264776	0.0695303	Exp1	Unit1	DC	DC1	17	A2	YES
Exp1_17D2_2	0.2288960	0.0455693	Exp1	Unit2	DC	DC2	17	A2	YES
Exp1_17T1_2	0.2587796	0.0884254	Exp1	Unit1	TC	TC1	17	A2	YES
Exp1_17T2_2	0.2601908	0.1170307	Exp1	Unit2	TC	TC2	17	A2	YES
Exp1_20A1	0.2592540	0.1419959	Exp1	Unit1	AC	AC1	20	NO	YES
Exp1_20A2	0.2517814	0.1363950	Exp1	Unit2	AC	AC2	20	NO	YES
Exp1_20D1	0.2039536	0.0762874	Exp1	Unit1	DC	DC1	20	NO	YES
Exp1_20D2	0.2156043	0.0351714	Exp1	Unit2	DC	DC2	20	NO	YES
Exp1_20T1	0.2424306	0.1104838	Exp1	Unit1	TC	TC1	20	NO	YES
Exp1_20T2	0.2484694	0.1037655	Exp1	Unit2	TC	TC2	20	NO	YES
Exp1_21A1	0.2536555	0.1174449	Exp1	Unit1	AC	AC1	21	NO	YES
Exp1_21A2	0.2604426	0.1301304	Exp1	Unit2	AC	AC2	21	NO	YES
Exp1_21D1	0.2123776	0.0742765	Exp1	Unit1	DC	DC1	21	NO	YES
Exp1_21D2	0.2081537	0.0575063	Exp1	Unit2	DC	DC2	21	NO	YES
Exp1_21T1	0.2398925	0.1198696	Exp1	Unit1	TC	TC1	21	NO	YES
Exp1_21T2	0.2491966	0.1015611	Exp1	Unit2	TC	TC2	21	NO	YES
Exp1_23A1_2	0.2505437	0.1136735	Exp1	Unit1	AC	AC1	22	A2	YES
Exp1_23A2_2	0.2564423	0.1163847	Exp1	Unit2	AC	AC2	22	A2	YES
Exp1_23D1_2	0.2128353	0.0555137	Exp1	Unit1	DC	DC1	22	A2	YES
Exp1_23D2_2	0.2252923	0.0451506	Exp1	Unit2	DC	DC2	22	A2	YES
Exp1_23T1_2	0.2460740	0.1112777	Exp1	Unit1	TC	TC1	22	A2	YES
Exp1_23T2_2	0.2509772	0.1037091	Exp1	Unit2	TC	TC2	22	A2	YES
Exp1_2A1_2	-0.0542209	-0.4860391	Exp1	Unit1	AC	AC1	2	A2	YES
Exp1_2A2_2	-0.0616063	-0.4857363	Exp1	Unit2	AC	AC2	2	A2	YES
Exp1_2D1_2	-0.0537886	-0.5197329	Exp1	Unit1	DC	DC1	2	A2	YES
Exp1_2D2_2	-0.0478566	-0.5097330	Exp1	Unit2	DC	DC2	2	A2	YES
Exp1_2T1_2	-0.0421125	-0.5147059	Exp1	Unit1	TC	TC1	2	A2	YES
Exp1_2T2_2	-0.0471718	-0.5119103	Exp1	Unit2	TC	TC2	2	A2	YES
Exp1_5A1	0.2458645	0.0577689	Exp1	Unit1	AC	AC1	5	NO	YES
Exp1_5A2	0.2108324	-0.0430012	Exp1	Unit2	AC	AC2	5	NO	YES
Exp1_5D1	0.0931342	-0.2867966	Exp1	Unit1	DC	DC1	5	NO	YES
Exp1_5D2	0.0600850	-0.3152770	Exp1	Unit2	DC	DC2	5	NO	YES
Exp1_5T1	0.1995305	-0.1289747	Exp1	Unit1	TC	TC1	5	NO	YES
Exp1_5T2	0.1359410	-0.2232990	Exp1	Unit2	TC	TC2	5	NO	YES
Exp1_6A1	0.2356668	0.0865840	Exp1	Unit1	AC	AC1	6	NO	YES
Exp1_6A2	0.2433493	0.0717020	Exp1	Unit2	AC	AC2	6	NO	YES
Exp1_6D1	0.1794178	-0.1574569	Exp1	Unit1	DC	DC1	6	NO	YES
Exp1_6D2	0.1493715	-0.1865668	Exp1	Unit2	DC	DC2	6	NO	YES
Exp1_6T1	0.2425770	-0.0131605	Exp1	Unit1	TC	TC1	6	NO	YES
Exp1_6T2	0.2225351	-0.0764632	Exp1	Unit2	TC	TC2	6	NO	YES
Exp1_7A1_2	0.2410020	0.0642033	Exp1	Unit1	AC	AC1	7	A2	YES
Exp1_7A2_2	0.2275324	0.0242377	Exp1	Unit2	AC	AC2	7	A2	YES
Exp1_7D1_2	0.2167371	-0.0834913	Exp1	Unit1	DC	DC1	7	A2	YES
Exp1_7D2_2	0.1987917	-0.1155900	Exp1	Unit2	DC	DC2	7	A2	YES
Exp1_7T1_2	0.2514338	0.0032591	Exp1	Unit1	TC	TC1	7	A2	YES
Exp1_7T2_2	0.2372218	-0.0457467	Exp1	Unit2	TC	TC2	7	A2	YES
Exp2_101	-0.3946628	-0.0125345	Exp2	Unit1	AC	AC1	1	NO	YES
Exp2_107	-0.4703817	0.1407767	Exp2	Unit1	AC	AC1	21	NO	YES
Exp2_109	-0.3302521	-0.0917644	Exp2	Unit1	DC	DC1	1	NO	YES
Exp2_112	-0.5030497	0.1166510	Exp2	Unit1	AC	AC1	7	NO	YES
Exp2_113	-0.4715645	0.0966926	Exp2	Unit1	DC	DC1	5	NO	YES
Exp2_114	-0.3844721	0.0978012	Exp2	Unit1	DC	DC1	21	NO	YES
Exp2_125	-0.4310609	0.1020624	Exp2	Unit1	DC	DC1	13	NO	YES
Exp2_129	-0.4229217	0.0959367	Exp2	Unit1	DC	DC1	15	NO	YES
Exp2_15	-0.4717850	0.1129392	Exp2	Unit1	DC	DC1	7	NO	YES
Exp2_18	-0.3799263	0.1094529	Exp2	Unit1	DC	DC1	25	NO	YES
Exp2_20	-0.4298488	0.1078088	Exp2	Unit1	DC	DC1	11	NO	YES
Exp2_22	-0.4982336	0.1101436	Exp2	Unit1	AC	AC1	29	NO	YES
Exp2_25	-0.4088843	0.0363510	Exp2	Unit1	DC	DC1	3	NO	YES
Exp2_26	-0.4342018	0.1012039	Exp2	Unit1	DC	DC1	9	NO	YES
Exp2_3	-0.4818679	0.1309512	Exp2	Unit1	AC	AC1	25	NO	YES
Exp2_36	-0.3682212	0.1018673	Exp2	Unit1	DC	DC1	29	NO	YES
Exp2_40	-0.4954695	0.1195638	Exp2	Unit1	AC	AC1	13	NO	YES
Exp2_43	-0.4869123	0.1117271	Exp2	Unit1	AC	AC1	31	NO	YES
Exp2_50	-0.4907559	0.1237128	Exp2	Unit1	AC	AC1	19	NO	YES
Exp2_51	-0.4525669	0.0620748	Exp2	Unit1	AC	AC1	3	NO	YES
Exp2_58	-0.4923113	0.1170102	Exp2	Unit1	AC	AC1	17	NO	YES
Exp2_60	-0.4914208	0.1211465	Exp2	Unit1	AC	AC1	11	NO	YES
Exp2_61	-0.3504377	0.0826640	Exp2	Unit1	DC	DC1	23	NO	YES
Exp2_62	-0.4981926	0.1126525	Exp2	Unit1	AC	AC1	9	NO	YES
Exp2_68	-0.3678534	0.0994831	Exp2	Unit1	DC	DC1	31	NO	YES
Exp2_7	-0.3129596	-0.0551986	Exp2	Fecal	Fecal	Fecal	0	NO	YES
Exp2_70	-0.4418437	0.1023092	Exp2	Unit1	DC	DC1	17	NO	YES
Exp2_77	-0.4270004	0.0976050	Exp2	Unit1	DC	DC1	19	NO	YES
Exp2_78	-0.5025657	0.1174558	Exp2	Unit1	AC	AC1	27	NO	YES
Exp2_8	-0.3910134	0.1084368	Exp2	Unit1	DC	DC1	27	NO	YES
Exp2_83	-0.4604354	0.1398532	Exp2	Unit1	AC	AC1	23	NO	YES
Exp2_88	-0.4943289	0.1122258	Exp2	Unit1	AC	AC1	15	NO	YES
Exp2_99	-0.5148743	0.1127323	Exp2	Unit1	AC	AC1	5	NO	YES

10.0.1 Beta Diversity

ggplot(ord_DataFrame, aes(x = X45.7., y = X19.4., color = Compartment_Unit, shape = Unit)) +
  geom_point(size = 5) #+

  #scale_shape_manual(values = c(18, 19, 17)) +
  #theme_pubr(border = TRUE) +
  #coord_fixed(ratio = 1)

10.1 Adding color and more nuances

unique(ord_DataFrame$Compartment_Unit)

## [1] "Fecal" "AC1"   "AC2"   "DC1"   "DC2"   "TC1"   "TC2"

# compartment Unit
compartment_unit_col <- c("Fecal" = "#264D59", "AC1" = "#77A515", "TC1" = "#D46C4E", "DC1" = "#43978D", "AC2" = "#77A515", "TC2" = "#D46C4E", "DC2" = "#43978D")

ordplot2 <- ggplot(ord_DataFrame, aes(x = X45.7., y = X19.4., color = Compartment_Unit, shape = Unit)) +
  geom_hline(yintercept = 0, linetype = 'dashed', alpha = 0.3) + 
  geom_vline(xintercept = 0, linetype = 'dashed', alpha = 0.3) +
  geom_point(size = 5) + 
  #geom_text_repel(aes(label = Study), nudge_x = 0.06, size = 3.0, segment.alpha = 0.5) +
  scale_shape_manual(values = c(18, 19, 17)) +  
  theme_pubr(border = TRUE) +
  coord_fixed(ratio = 1) + # Keep aspect ratio 1:1
  theme(axis.text = element_text(size = 14),
        axis.text.x = element_text(size = 12, hjust = 0.5),
        axis.title.y = element_text(size = 18),
        legend.text = element_text(size = 14),
        legend.title = element_text(size = 0),
        legend.position = "bottom", #top, null etc
        axis.title.x = element_text(size = 18),
        strip.text.x = element_text(size = 20, face = "bold")) +
        scale_color_manual(values = compartment_unit_col) +
  labs(x = "PCo1 [45.7%]", y = "PCo2 [19.4%]", color = "Compartment_Unit", shape = "Unit") #+
  #annotate("text", x = min(ord_DataFrame$X45.7.), y = min(ord_DataFrame$X19.4.), 
           #label = "Exp2", hjust = 0.1, vjust = 0.4, size = 5, color = "black")

# To view the plot
print(ordplot2)

11 Heatmap

12 HeatMAp and BarPlot

Step 1: Filter the data: Remove ASVs that do not show appear more than 3 times in more than 30% the samples
Step 2: Transform the data: Relative Abundance

12.0.1 HeatMap

heat_df <- read.table("data/raw/03_HeatMap_Exp1_DCs.tsv", header=T, sep="\t", row.names=1, check.names=T)
class(heat_df)

## [1] "data.frame"

heat_mat <- as.matrix(heat_df)
class(heat_mat)

## [1] "matrix" "array"

13 Filter top 20

# Step 1: Calculate row sums or another measure to identify top taxa
heat_df$Total <- rowSums(heat_df) # or use `rowMeans` if preferred

# Step 2: Filter the top 20 rows based on Total
top20_data <- heat_df %>%
  arrange(desc(Total)) %>%
  slice(1:20) %>%
  select(-Total)

# Step 3: Convert to matrix for ComplexHeatmap
data_matrix <- as.matrix(top20_data)
#data_matrix <- as.matrix(heat_df)

14 Plot

library(ComplexHeatmap)
library(circlize)  # For colorRamp2 function if needed

## ========================================
## circlize version 0.4.16
## CRAN page: https://cran.r-project.org/package=circlize
## Github page: https://github.com/jokergoo/circlize
## Documentation: https://jokergoo.github.io/circlize_book/book/
## 
## If you use it in published research, please cite:
## Gu, Z. circlize implements and enhances circular visualization
##   in R. Bioinformatics 2014.
## 
## This message can be suppressed by:
##   suppressPackageStartupMessages(library(circlize))
## ========================================

# Create heatmap with ComplexHeatmap
Heatmap(data_matrix,
        name = "Abundance",
        col = colorRamp2(c(min(data_matrix), median(data_matrix), max(data_matrix)), 
                         c("blue", "white", "red")),
        show_row_names = TRUE,
        show_column_names = TRUE,
        cluster_rows = TRUE,
        cluster_columns = TRUE
)

14.1 more

# Define sample compartments
ncol(data_matrix)

## [1] 13

# Create Compartment labels for the samples, repeating "DC1" for all columns in data_matrix
compartment <- rep("DC1", ncol(data_matrix))

# Check if the lengths match
length(compartment) == ncol(data_matrix)  # Should return TRUE

## [1] TRUE

# Colors for compartments
compartment_colors <- c("DC1" = "#43978D")


# Create the annotation
sample_annotation <- HeatmapAnnotation(
    Compartment = compartment,
    col = list(Compartment = compartment_colors)
)

# Create the heatmap with the annotation
Heatmap(
  data_matrix,
  name = "Abundance",
  col = colorRamp2(
    c(min(data_matrix), median(data_matrix), max(data_matrix)),  # Color scale points
    c("blue", "white", "red")  # Colors corresponding to min, median, and max values
  ),
  show_row_names = TRUE,       # Show row names
  show_column_names = TRUE,     # Show column names
  cluster_rows = TRUE,          # Cluster rows
  cluster_columns = TRUE,       # Cluster columns
  top_annotation = HeatmapAnnotation(
    Compartment = anno_simple(
      compartment,               # Variable for compartment annotation
      col = compartment_colors   # Custom colors for compartments
    )
  )
)

15 Pheatmap

## Change colors
colsHeat<- c("#F7F7F7", "#92C5DE", "#0571B0", "#F4A582", "#CA0020")

# Create an annotation dataframe
annotation_df <- data.frame(Compartment = compartment)

# Define annotation colors
annotation_colors <- list(Compartment = c("DC1" = "#43978D"))

# Plot heatmap using pheatmap
pheatmap(data_matrix,
         cluster_cols = FALSE,
         cluster_rows = TRUE,
         #scale = "column",
         #gaps_row = 5, 
         clustering_distance_rows = "euclidean",
         clustering_distance_cols  = "euclidean",
         annotation_colors = annotation_colors, 
         annotation_col = annotation_df,  
         show_colnames = TRUE,
         color = colorRampPalette(c(colsHeat))(50),
         border_color = "#f8edeb",
         display_numbers = FALSE)

16 Sort and “normalization”

The code is performing a column-wise normalization on data_matrix by dividing each element in a column by the mean of that column.

Purpose of the Code The result, stored in data, is a transformed version of data_matrix where each column has been scaled so that the average value in each column is 1. This transformation is often done to normalize the data across columns to account for differences in scale or to control for sample-specific variation in abundance data.

# Row-wise normalization
#data <- apply(data_matrix, 1, function(x) { x / mean(x) })

# Column-wise normalization
data <- apply(data_matrix, 2, function(x) { x / mean(x) })

# Different normalization
#sequencing_depth <- 20000
#read_counts_matrix <- data_matrix * sequencing_depth
# Step 2: Log-normalize each value in the matrix
#data <- log10(1 + read_counts_matrix) / max(log10(1 + read_counts_matrix))

# Sort by Days
colnames(data) <- colnames(data)[order(as.numeric(gsub("Exp1_(\\d+).*", "\\1", colnames(data))))]

pheatmap(data,
         cluster_cols = FALSE,
         cluster_rows = TRUE,
         #scale = "column",
         #gaps_row = 5, 
         clustering_distance_rows = "euclidean",
         clustering_distance_cols  = "euclidean",
         annotation_colors = annotation_colors, 
         annotation_col = annotation_df,  # Add annotation dataframe here
         show_colnames = TRUE,
         color = colorRampPalette(c(colsHeat))(50),
         border_color = "#f8edeb",
         display_numbers = FALSE)

17 Iteractive

18 Plotly

library(plotly)
# Create the main heatmap for your data
p <- plot_ly(
    x = colnames(data),  # Column names as x-axis
    y = rownames(data),   # Row names as y-axis
    z = data,             # Data matrix
    type = "heatmap", 
    colors = colsHeat,
    showscale = TRUE,
    colorbar = list(title = "Abundance")  # Optional colorbar title
) %>%
    layout(
        margin = list(l = 120),  # Space for row names on the left
        xaxis = list(showticklabels = TRUE, ticks = ""),
        yaxis = list(tickvals = 1:nrow(data), ticktext = rownames(data))
    )

p

# Create the compartment annotation heatmap (only DC1, shown in #43978D)
compartment_annotation <- rep(0, ncol(data))  # Only 0s for DC1

p_compartment <- plot_ly(
    x = colnames(data),
    y = "Compartment",  # Annotation row title
    z = matrix(compartment_annotation, nrow = 1),  # Annotation as a single-row matrix
    type = "heatmap",
    colorscale = list(list(0, "#43978D"), list(1, "#43978D")),  # Fixed color for DC1 only
    showscale = FALSE  # No colorbar for annotation
) %>%
    layout(
        xaxis = list(showticklabels = TRUE, ticks = ""),
        yaxis = list(
            tickvals = c(0),       # Position the annotation title
            ticktext = "Compartment"
        )
    )

# Combine the main heatmap and the annotation strip
subplot(p_compartment, p, nrows = 2, heights = c(0.1, 0.9), shareX = TRUE)

Workshop: Introduction to Data Visualization using R

15-Nov-2024

1 Introduction to data visualization

2 Downloading the files and making a Dir called Raw

3 Loading the first file

4 Summary: Sample Information

5 Filtering the data using Dyplr package

6 BoxPlot

7 Sort the compartment and add color

8 Plotting

9 facet_wrap() funcion, mutate

9.1 Longitudinal

10 Beta Diversity, PCA

10.0.1 Beta Diversity

10.1 Adding color and more nuances

11 Heatmap

12 HeatMAp and BarPlot

12.0.1 HeatMap

13 Filter top 20

14 Plot

14.1 more

15 Pheatmap

16 Sort and “normalization”

17 Iteractive

18 Plotly

19 Different package